© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105852
    Prev
    Next
    INDEX
    Explanations

    significant statistical terms and phrases related to study results and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.78
    tvguidetime
    -0.61
     ſont
    -0.60
     iconLine
    -0.60
    URBANA
    -0.57
     faſt
    -0.56
     Administrativna
    -0.55
     propOrder
    -0.55
    ロウィン
    -0.53
     Numerade
    -0.53
    POSITIVE LOGITS
     tartalomajánló
    0.34
     nhất
    0.34
     especially
    0.34
     recently
    0.33
     probably
    0.31
     surla
    0.30
     especialmente
    0.29
     but
    0.28
    especially
    0.28
    不過
    0.28
    Activations Density 0.096%

    No Known Activations